Sequence-to-Sequence Pre-training with Unified Modality Masking for Visual Document Understanding

no code implementations • 16 May 2023 • Shuwei Feng, Tianyang Zhan, Zhanming Jie, Trung Quoc Luong, Xiaoran Jin

This paper presents GenDoc, a general sequence-to-sequence document understanding model pre-trained with unified masking across three modalities: text, image, and layout.

Decoder document understanding +2